Milvus – Medium

Milvus

Pinned

In

Vector Database for AI

by

Milvus

·

Dec 5, 2022

What is a Vector Database?

An introduction to the concepts related to vector database.

What is a Vector Database?

Milvus

·

1d ago

Beyond the TurboQuant-RaBitQ Debate: Why Vector Quantization Matters for AI Infrastructure Costs

Google’s TurboQuant paper (ICLR 2026) reported 6x KV cache compression with near-zero accuracy loss — results striking enough to wipe $90…

Beyond the TurboQuant-RaBitQ Debate: Why Vector Quantization Matters for AI Infrastructure Costs

Milvus

·

1d ago

Is MCP Dead? What We Learned Building with MCP, CLI, and Agent Skills

When Perplexity’s CTO Denis Yarats said at ASK 2026 that the company was deprioritizing MCP internally, it set off the usual cycle. YC CEO…

Is MCP Dead? What We Learned Building with MCP, CLI, and Agent Skills

Milvus

·

2d ago

Harness Engineering: The Execution Layer AI Agents Actually Need

Mitchell Hashimoto built HashiCorp and co-created Terraform. In February 2026, he published a blog post describing a habit he’d developed…

Harness Engineering: The Execution Layer AI Agents Actually Need

Milvus

·

2d ago

Interview with RaBitQ Authors: The TurboQuant Dispute and Why the Storage Selloff Was a False Alarm

Google’s TurboQuant paper claimed 6x compression, 8x speedup, and near-zero accuracy loss for vector representations. After it was…

Interview with RaBitQ Authors: The TurboQuant Dispute and Why the Storage Selloff Was a False Alarm

Milvus

·

3d ago

We Built Graph RAG Without the Graph Database

TL;DR: Do you actually need a graph database for Graph RAG? No. Put entities, relations, and passages into Milvus. Use subgraph expansion…

We Built Graph RAG Without the Graph Database

Milvus

·

3d ago

How to Fix Hermes Agent’s Learning Loop with Milvus 2.6 Hybrid Search

Hermes Agent has been everywhere lately. Built by Nous Research, Hermes is a self-hosted personal AI agent that runs on your own hardware…

How to Fix Hermes Agent’s Learning Loop with Milvus 2.6 Hybrid Search

Milvus

·

4d ago

Claude Context: Reduce Claude Code Token Usage with Milvus-Powered Code Retrieval

Large context windows make AI coding agents feel limitless, right up until they start reading half your repository to answer one question…

Claude Context: Reduce Claude Code Token Usage with Milvus-Powered Code Retrieval

Milvus

·

4d ago

How to Add Long-Term Memory to Anthropic’s Managed Agents with Milvus

Anthropic’s Managed Agents make agent infrastructure resilient. A 200-step task now survives a harness crash, a sandbox timeout, or a…

How to Add Long-Term Memory to Anthropic’s Managed Agents with Milvus

Milvus

·

Jun 11

DeepSeek V4 vs GPT-5.5 vs Qwen3.6: Which Model Should You Use?

New model releases are moving faster than production teams can evaluate them. DeepSeek V4, GPT-5.5, and Qwen3.6–35B-A3B all look strong on…

DeepSeek V4 vs GPT-5.5 vs Qwen3.6: Which Model Should You Use?

Milvus

Milvus

Milvus is the leading open-source vector database built to power embedding similarity search and AI applications. GitHub: https://github.com/milvus-io/milvus

Following

Help

Status

About

Careers

Press

Blog

Store

Privacy

Rules

Terms

Text to speech